New paper out on identifying emergency department patients at high risk for opioid overdose using natural language processing and machine learning

Read the full paper here and see key points from the paper below!

Key Points

• Objective: The purpose of this study is to develop a modeling process that can eventually be implemented in clinical settings, informing emergency medicine providers of opioid overdose risks, assisting them in making decisions about care delivered in the Emergency Department (ED), and assisting discharge planning and coordination of follow-up care

  Findings: Feature selection reduced the feature matrix from 1336 to 50 features, with 37 originating from Electronic Health Records clinical notes. Using a probability of >0.5 as a predictor of opioid overdose death, all models demonstrated satisfactory calibration and excellent accuracy, precision, and recall across all models (averaging 92 % accuracy, 75 % precision and 57 % recall)

  Conclusion: Machine Learning algorithms based on structured and unstructured EHR can successfully classify patients at risk of fatal opioid overdose. Prospectively, these tools can be used to identify patients that may benefit from interventions to reduce their risk of opioid overdose death. The development of these predictive models may improve the timeliness and efficacy of clinical decision making and ED-initiated services for opioid use disorders.